drm/xe/pf: Reset GuC VF config when unprovisioning critical resource

[ Upstream commit 33f17e2 ]

GuC firmware counts received VF configuration KLVs and may start
validation of the complete VF config even if some resources where
unprovisioned in the meantime, leading to unexpected errors like:

 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/contexts_quota
 $ echo 0 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/contexts_quota
 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/doorbells_quota
 $ echo 0 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/doorbells_quota
 $ echo 1 | sudo tee /sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/ggtt_quota
 tee: '/sys/kernel/debug/dri/0000:00:02.0/gt0/vf1/ggtt_quota': Input/output error

To mitigate this problem trigger explicit VF config reset after
unprovisioning any of the critical resources (GGTT, context or
doorbell IDs) that GuC is monitoring.

Signed-off-by: Michal Wajdeczko <[email protected]>
Reviewed-by: Michał Winiarski <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Sasha Levin <[email protected]>

Author: mwajdecz

drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c

@@ -323,6 +323,26 @@ static int pf_push_full_vf_config(struct xe_gt *gt, unsigned int vfid)
 	return err;
 }
 
+static int pf_push_vf_cfg(struct xe_gt *gt, unsigned int vfid, bool reset)
+{
+	int err = 0;
+
+	xe_gt_assert(gt, vfid);
+	lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
+
+	if (reset)
+		err = pf_send_vf_cfg_reset(gt, vfid);
+	if (!err)
+		err = pf_push_full_vf_config(gt, vfid);
+
+	return err;
+}
+
+static int pf_refresh_vf_cfg(struct xe_gt *gt, unsigned int vfid)
+{
+	return pf_push_vf_cfg(gt, vfid, true);
+}
+
 static u64 pf_get_ggtt_alignment(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
@@ -419,6 +439,10 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 			return err;
 
 		pf_release_vf_config_ggtt(gt, config);
+
+		err = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(err))
+			return err;
 	}
 	xe_gt_assert(gt, !xe_ggtt_node_allocated(config->ggtt_region));
 
@@ -744,6 +768,10 @@ static int pf_provision_vf_ctxs(struct xe_gt *gt, unsigned int vfid, u32 num_ctx
 			return ret;
 
 		pf_release_config_ctxs(gt, config);
+
+		ret = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(ret))
+			return ret;
 	}
 
 	if (!num_ctxs)
@@ -1041,6 +1069,10 @@ static int pf_provision_vf_dbs(struct xe_gt *gt, unsigned int vfid, u32 num_dbs)
 			return ret;
 
 		pf_release_config_dbs(gt, config);
+
+		ret = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(ret))
+			return ret;
 	}
 
 	if (!num_dbs)
@@ -2003,10 +2035,7 @@ int xe_gt_sriov_pf_config_push(struct xe_gt *gt, unsigned int vfid, bool refresh
 	xe_gt_assert(gt, vfid);
 
 	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
-	if (refresh)
-		err = pf_send_vf_cfg_reset(gt, vfid);
-	if (!err)
-		err = pf_push_full_vf_config(gt, vfid);
+	err = pf_push_vf_cfg(gt, vfid, refresh);
 	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
 
 	if (unlikely(err)) {